© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3773
    Prev
    Next
    INDEX
    Explanations

    instances of the words "till" and "until"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ckså
    -0.47
     gambe
    -0.43
    erba
    -0.42
    elser
    -0.40
    crombie
    -0.40
    leich
    -0.38
     păr
    -0.38
     lagt
    -0.37
     dår
    -0.37
     gesteld
    -0.37
    POSITIVE LOGITS
     until
    3.31
     till
    3.16
     Until
    3.08
    until
    3.05
    Until
    3.02
     hasta
    2.86
     untill
    2.75
    Till
    2.67
     Till
    2.63
     jusqu
    2.53
    Activations Density 0.103%

    No Known Activations